INDEX

Explanations

punctuation marks, particularly periods

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"Q" followed by a colon

np_acts-logits-general · gemini-2.0-flash

questions and explanations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nahilalakip

-1.10

 Roskov

-0.99

^(@)

-0.88

verständlich

-0.80

 ProtoMessage

-0.80

+#+#

-0.79

StoryboardSegue

-0.78

日閲覧

-0.77

Hauptartikel

-0.76

Diwedd

-0.75

POSITIVE LOGITS

 Worse

1.42

Worse

1.42

 worse

1.14

Fortunately

1.11

 Fortunately

1.10

Solution

1.07

 solution

1.06

 Solution

1.05

 Luckily

1.04

怎么办

1.04

Activations Density 0.437%

punctuation marks, particularly periods

"Q" followed by a colon

questions and explanations

No Comments

No Known Activations